# Toward Scalable Verification for Safety-Critical Deep Networks

arXiv: https://arxiv.org/abs/1801.05950 · HTML: https://mlsanity.com/paper/1801.05950/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jan 2018.

## Built on by (most cited first, 12 of 12)

- [Shallow Bayesian Meta Learning for Real-World Few-Shot Recognition](https://mlsanity.com/paper/2101.02833/) (2021)
- [Towards Scalable Verification of Deep Reinforcement Learning](https://mlsanity.com/paper/2105.11931/) (2021)
- [Verifying Learning-Based Robotic Navigation Systems](https://mlsanity.com/paper/2205.13536/) (2022)
- [An Abstraction-Refinement Approach to Verifying Convolutional Neural Networks](https://mlsanity.com/paper/2201.01978/) (2022)
- [Pruning and Slicing Neural Networks using Formal Verification](https://mlsanity.com/paper/2105.13649/) (2021)
- [Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Framework](https://mlsanity.com/paper/2109.09829/) (2021)
- [Minimal Multi-Layer Modifications of Deep Neural Networks](https://mlsanity.com/paper/2110.09929/) (2021)
- [Verification-Guided Shielding for Deep Reinforcement Learning](https://mlsanity.com/paper/2406.06507/) (2024)
- [veriFIRE: Verifying an Industrial, Learning-Based Wildfire Detection System](https://mlsanity.com/paper/2212.03287/) (2022)
- [Verifying Generalization in Deep Learning](https://mlsanity.com/paper/2302.05745/) (2023)
- [Tighter Abstract Queries in Neural Network Verification](https://mlsanity.com/paper/2210.12871/) (2022)
- [Safe and Reliable Training of Learning-Based Aerospace Controllers](https://mlsanity.com/paper/2407.07088/) (2024)

## Abstract (arXiv)

The increasing use of deep neural networks for safety-critical applications, such as autonomous driving and flight control, raises concerns about their safety and reliability. Formal verification can address these concerns by guaranteeing that a deep learning system operates as intended, but the state of the art is limited to small systems. In this work-in-progress report we give an overview of our work on mitigating this difficulty, by pursuing two complementary directions: devising scalable verification techniques, and identifying design choices that result in deep learning systems that are more amenable to verification.